ULTRA LOW COMPLEXITY DEEP LEARNING BASED NOISE SUPPRESSION

Abstract

This paper introduces an innovative method for reducing the computational complexity of deep neural networks in real-time speech enhancement on resource-constrained devices. The proposed approach utilizes a two-stage processing framework, employing channelwise feature reorientation to reduce the computational load of convolutional operations. By combining this with a novel power law compression technique for enhanced perceptual quality, this approach achieves noise suppression performance comparable to state-of-the-art methods. Our proposed model has 688K parameters and achieves 12.7% real time factor on a single core of an A53 processor with a complexity of 0.097 GMACs.

Processing Methods

In our work, for the listening test we evaluate our two proposed methods, ULCNet_Freq (ULCNetFreq) and ULCNet_MS (ULCNetMS) against three existing approaches from the literature: FullSubNet+, DeepFilterNet and DeepFilterNet2.

Following you can find some samples from the listening tests:

1. Preference Test Samples --> Go to the samples

2. MUSHRA Test Samples --> Go to the samples

1. Preference Test Samples

Item 1

Item 2

Item 3

Item 4

Item 5

2. MUSHRA Test Samples

Item 1

Item 2

Item 3

Item 4

Item 5

---

---

Conditions of Use

1.Fraunhofer IIS generated this sound material based on material that is publicly available on DNS Challenge

2.The content has been processed using generally accepted rules of technology as well as scientific care, but not actual attainment of any expected feature.

3. With the exception of willful intent or gross negligence, Fraunhofer IIS shall not be liable that Open Source software or other third-party software is free from any error or claim or its fitness for a particular purpose, even if included within the Sound Material.

4.The Sound Material shall only be used for testing and appreciating noise reduction techniques and shall not be copied, publicly transmitted, distributed, lent or modified for any other reason.

5.No representation or warranties are made or implied regarding the accuracy, non-infringement, or fitness for a particular purpose of Sound Material.

6.Copyright and Permission notice shall be duplicated whenever Sound Material is copied, distributed, or publicly transmitted.

6.The Sound material cannot be distributed with charge. --> Go to Top